CVE Daily

CVE-2025-46059

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vuln...

Critical CVSS 9.8

Overview

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices.

CWE: CWE-94 Published: 2025-07-29T15:15:35.003
Risk analysis

This vulnerability is rated 🔴 CRITICAL.

  • CVSS: 9.8 (CRITICAL)
  • Detected tags: rce (tag impact: VERY HIGH)

Recommended actions:

  • Patch/upgrade immediately (remote code execution).
  • Reduce exposure (WAF/segmentation), minimize attack surface.

Recommended tools

Tags